Creator
StepFun
Released
2026-02-02
Intelligence
37.8
Artificial Analysis Index
Coding
31.6
Artificial Analysis Index
In $/1M
$0.10
input tokens
Out $/1M
$0.30
output tokens
Blended $/1M
$0.15
3:1 blended
Speed
178
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
83
Humanity’s Last Exam
19
MMLU-Pro—
SciCode
40
LiveCodeBench—
MATH-500—
AIME 2025—
τ²-Bench (agentic)
94
Terminal-Bench Hard
27
IFBench
65